Back to skill

Security audit

conversations

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to do what it advertises, but it creates a persistent plaintext searchable database of OpenClaw conversations and recommends recurring imports without enough privacy controls or cleanup guidance.

Review before installing. Use it only on a trusted single-user machine and assume conversations.db will contain plaintext copies of sensitive prompts, code, credentials, and assistant replies. Avoid enabling the cron import unless you intentionally want future sessions archived, place the database in a private directory, restrict file permissions, and delete the database when you no longer need the archive.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/import_sessions.py:183
Finding

Conversation History Is Consolidated in an Unencrypted SQLite Database Without Explicit Permission Hardening

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to import prior session history into a local SQLite database without clearly warning that this will duplicate potentially sensitive conversations into a new persistent store. This increases the risk of unintentionally retaining secrets, personal data, or confidential prompts in a searchable database that may have different access controls or backup behavior than the original session files.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The cron example encourages unattended recurring import of new conversation data but does not warn users that sensitive future sessions will be continuously ingested automatically. This can silently expand the amount of retained searchable data over time, increasing exposure in case of local compromise, shared workstation access, or accidental indexing of conversations users did not intend to archive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all user-facing documentation in Chinese, and there is no indication that the language choice is optional, configurable, or justified as a region-specific requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring and all visible status/error messages are written only in Chinese, which imposes a specific language on users without offering a choice. The policy for SQP-3 applies to code files when natural-language strings enforce a locale or language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Natural-language strings throughout the file, including the module description and all CLI messages, are hard-coded in Chinese. There is no user opt-in, language selection mechanism, or documented justification that this skill is intended only for a Chinese-language environment.

Content

No source excerpt is available for this finding.

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · scripts/query_conversations.py (reported line 12)May include surrounding context.

python
import sys
from pathlib import Path

SESSION_KEY_RE = __import__("re").compile(r"agent:main:(?:session:)?(?P<key>[^:]+)")


def get_db_path():

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script is explicitly designed to search and print conversation history, which can include secrets, personal data, tokens, or other sensitive operational context, yet it provides no warning, confirmation, masking, or output-safety controls. In this skill context, the database is a 'memory' store of prior sessions, so accidental disclosure to terminals, logs, screen recordings, or shared shells is a realistic confidentiality risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The natural-language content of the skill is entirely in Chinese, which can effectively force a specific language on users without opt-in. The policy requires either offering language choice or clearly documenting and justifying a locale-specific scope.

Content

No source excerpt is available for this finding.